© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1864
    Prev
    Next
    INDEX
    Explanations

    word or title fragment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     own
    -0.26
    abal
    -0.21
     afford
    -0.20
     mad
    -0.20
     мало
    -0.20
    alar
    -0.20
    aling
    -0.20
    _flutter
    -0.20
     Asia
    -0.19
     Peb
    -0.19
    POSITIVE LOGITS
    ¢åįķ
    0.23
    åĸŁ
    0.21
    oard
    0.21
    ä¸İåIJ¦
    0.21
    ä½Ĩä¸įéĻIJäºİ
    0.20
     пÑĢоизводÑģÑĤва
    0.20
    å¾Īæ¼Ĥ亮
    0.20
     OPTIONAL
    0.20
    ä¸ĢåIJ¬
    0.20
     uczniów
    0.19
    Activations Density 0.145%

    No Known Activations